test_deepseek_v3_basic.py

import unittest
from types import SimpleNamespace

import requests

from sglang.srt.utils import kill_process_tree
from sglang.test.few_shot_gsm8k import run_eval as run_eval_few_shot_gsm8k
from sglang.test.send_one import BenchArgs, send_one_prompt
from sglang.test.test_utils import (
    DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
    DEFAULT_URL_FOR_TEST,
    CustomTestCase,
    is_in_amd_ci,
    is_in_ci,
    popen_launch_server,
    write_github_step_summary,
)

FULL_DEEPSEEK_V3_MODEL_PATH = "deepseek-ai/DeepSeek-V3-0324"


class TestDeepseekV3Basic(CustomTestCase):
    @classmethod
    def setUpClass(cls):
        cls.model = FULL_DEEPSEEK_V3_MODEL_PATH
        cls.base_url = DEFAULT_URL_FOR_TEST
        other_args = ["--trust-remote-code", "--tp", "8"]
        cls.process = popen_launch_server(
            cls.model,
            cls.base_url,
            timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
            other_args=other_args,
        )

    @classmethod
    def tearDownClass(cls):
        kill_process_tree(cls.process.pid)

    def test_a_gsm8k(
        self,
    ):  # Append an "a" to make this test run first (alphabetically) to warm up the server
        args = SimpleNamespace(
            num_shots=8,
            data_path=None,
            num_questions=1400,
            parallel=1400,
            max_new_tokens=512,
            host="http://127.0.0.1",
            port=int(self.base_url.split(":")[-1]),
        )
        metrics = run_eval_few_shot_gsm8k(args)
        print(f"{metrics=}")

        if is_in_ci():
            write_github_step_summary(
                f"### test_gsm8k (deepseek-v3)\n" f'{metrics["accuracy"]=:.3f}\n'
            )
            self.assertGreater(metrics["accuracy"], 0.935)

    def test_bs_1_speed(self):
        args = BenchArgs(port=int(self.base_url.split(":")[-1]), max_new_tokens=2048)
        acc_length, speed = send_one_prompt(args)

        print(f"{speed=:.2f}")

        if is_in_ci():
            write_github_step_summary(
                f"### test_bs_1_speed (deepseek-v3)\n" f"{speed=:.2f} token/s\n"
            )
            if is_in_amd_ci():
                self.assertGreater(speed, 12)
            else:
                self.assertGreater(speed, 75)


if __name__ == "__main__":
    unittest.main()